© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 19324
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_40_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     WHEN
    0.36
     PAINT
    0.36
     hub
    0.35
     Beethoven
    0.35
     Larissa
    0.34
     Beaux
    0.34
    器
    0.34
     schwar
    0.33
     पेस्ट
    0.32
     રાશિ
    0.32
    POSITIVE LOGITS
    舂
    0.42
     Gerv
    0.37
     sheds
    0.37
    InstanceManager
    0.37
    اهده
    0.36
     প্রমাণ
    0.35
    '>
    0.34
     प्रस्ताव
    0.34
    టి
    0.34
     별
    0.34
    Activations Density 0.026%

    No Known Activations